ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation

• URL: http://arxiv.org/abs/2608.23429v1
• Date: Mon, 24 Aug 2026 16:06:11 GMT
• Title: ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation
• Abstract summary: Diffusion Transformers (DiTs) have shown strong performance in high-fidelity image generation, but their sampling process remains computationally intensive due to full model execution at every timestep.<n>We propose ChebBooster, a training-free extrapolation framework based on Chebyshev theory that achieves stable and efficient acceleration for DiTs.
• Score: 6.871887763122593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion Transformers (DiTs) have shown strong performance in high-fidelity image generation, but their sampling process remains computationally intensive due to full model execution at every timestep. While cache-based acceleration has been explored to mitigate inference cost, naive reuse schemes suffer from low accuracy over long intervals, and Taylor-series-based extrapolation methods often face instability caused by Runge oscillations. In this paper, we propose ChebBooster, a training-free extrapolation framework based on Chebyshev polynomial theory that achieves stable and efficient acceleration for DiTs. Specifically, we adopt the Barycentric formulation to evaluate Chebyshev approximants with high numerical stability and minimal overhead, and further decouple the extrapolation into an offline weight precomputation phase and a lightweight online application stage. Extensive experiments across three representative DiT-based models, including DiT-XL/2, PixArt-$Σ$, and FLUX.1-dev, demonstrate that ChebBooster achieves consistent improvements in visual quality and inference efficiency, reaching up to $3.68\times$ latency speedup and $5.12\times$ FLOPs reduction, outperforming existing training-free baselines under diverse generation tasks and resolutions.

Related papers

• Memory-Efficient Training-Free Acceleration of Diffusion Transformers with BaryCache [23.178001584385544]
  We propose a training-free acceleration method that performs stepwise forecasting for DiT sampling using a Barycentric Extrapolator.<n>Our approach provides a favorable trade-off between memory usage and perceptual quality, while delivering up to 3.30x end-to-end sampling speedup.
  arXiv  Detail & Related papers  (2026-08-24T16:11:56Z)
• BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusion Transformers Inference [7.024073219145713]
  Diffusion Transformers (DiTs) have demonstrated exceptional performance in high-fidelity image and video generation.<n>To alleviate their massive computational overhead, temporal feature caching has been proposed to bypass redundant computations.<n>We propose Barycentric Forecasting with Chebyshev Enhancement (BRACE) to address this bottleneck.
  arXiv  Detail & Related papers  (2026-08-04T11:24:53Z)
• Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models [91.19049123903137]
  Inference-time scaling for text-to-image generation has progressed from simple Best-of-$N$ sampling to guided search methods.<n>These approaches focus on when and how often to verify during denoising but largely treat the cost of generation itself as fixed.<n>We show that under wall-clock evaluation, simple BoN already matches or outperforms several guided search techniques.
  arXiv  Detail & Related papers  (2026-07-05T19:02:32Z)
• Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models [56.67321805551389]
  Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators.<n>The sampler, controlling the exploration behavior and denoising dynamics, is thus part of the policy.<n>We propose a new sampler that balances effective exploration with stability.
  arXiv  Detail & Related papers  (2026-05-22T11:37:22Z)
• DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling [18.524470249911232]
  Dynamic Gradient Weighting (DyWeight) is a lightweight, learning-based multi-step solver.<n>DyWeight learns unconstrained time-varying parameters that adaptively aggregate historical gradients.<n>Experiments on CIFAR-10, FFHQ, AFHQv2, ImageNet64, LSUN-Bedroom, Stable Diffusion and FLUX.1-dev demonstrate that DyWeight achieves superior visual fidelity and stability.
  arXiv  Detail & Related papers  (2026-03-12T07:01:44Z)
• Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration [58.19554276924402]
  We propose spectral diffusion feature forecaster (Spectrum) to enable global, long-range feature reuse with tightly controlled error.<n>We achieve up to 4.79$times$ speedup on FLUX.1 and 4.67$times$ speedup on Wan2.1-14B, while maintaining much higher sample quality compared with the baselines.
  arXiv  Detail & Related papers  (2026-03-02T08:59:11Z)
• FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformers [12.17745708847535]
  FREE is a novel framework that employs a lightweight drafter to perform feature-level autoregression with parallel verification.<n>Experiments on ImageNet-$5122$ show that FREE achieves up to $1.86 times$ acceleration, and FREE (relax) further reaches $2.25 times$ speedup.
  arXiv  Detail & Related papers  (2025-11-25T15:12:10Z)
• Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation [67.20779609022108]
  Flow matching models generate high-fidelity molecular geometries but incur significant computational costs during inference.<n>This work discusses a training-free caching strategy that accelerates molecular geometry generation.<n> Experiments on the GEOM-Drugs dataset demonstrate that caching achieves a twofold reduction in wall-clock inference time.
  arXiv  Detail & Related papers  (2025-10-06T09:49:14Z)
• RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer [86.57077884971478]
  Diffusion Transformers (DiTs) excel at visual generation yet remain hampered by slow sampling.<n>We introduce RAPID3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformers.<n>It delivers image-wise acceleration with zero updates to the base generator.<n>It achieves nearly 3x faster sampling with competitive generation quality.
  arXiv  Detail & Related papers  (2025-09-26T13:20:52Z)
• DiffusionNFT: Online Diffusion Reinforcement with Forward Process [99.94852379720153]
  Diffusion Negative-aware FineTuning (DiffusionNFT) is a new online RL paradigm that optimize diffusion models directly on the forward process via flow matching.<n>DiffusionNFT is up to $25times$ more efficient than FlowGRPO in head-to-head comparisons, while being CFG-free.
  arXiv  Detail & Related papers  (2025-09-19T16:09:33Z)
• EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving [64.15371139980802]
  Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP)<n>We show that different test-time scaling strategies for ATP models introduce significant computational overhead for inference.<n>We propose two complementary methods that can be integrated into a unified EconRL pipeline for amplified benefits.
  arXiv  Detail & Related papers  (2025-09-16T03:00:13Z)
• SADA: Stability-guided Adaptive Diffusion Acceleration [24.250318487331228]
  Diffusion models have achieved remarkable success in generative tasks but suffer from high computational costs.<n>Existing training-free acceleration strategies that reduce per-step computation cost, while effectively reducing sampling time, demonstrate low faithfulness.<n>We propose Stability-guided Adaptive Diffusion Acceleration (SADA), a novel paradigm that accelerates sampling of ODE-based generative models.
  arXiv  Detail & Related papers  (2025-07-23T02:15:45Z)
• Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models [21.961189407928853]
  We propose and analyze a training-free acceleration algorithm for SDE-style diffusion samplers, based on the KL Runge-Kutta method. The proposed sampler provably attains $varepsilon2$ error -- measured in divergence -- using $widetilde O(d3/2 / varepsilon)$ score function evaluations.
  arXiv  Detail & Related papers  (2024-10-07T05:34:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.